Computer vision in aseptic pharmaceutical manufacturing: a deep learning-based approach to vial inspection and pack formation during a lyophilizer loading cycle

Vision systems are powerful tools playing an increasingly important role in modern industry, to detect errors and maintain product standards. With the enlarged availability of affordable industrial cameras, computer vision algorithms have been increasingly applied in industrial manufacturing processes monitoring. Until a few years ago, industrial computer vision applications relied only on ad-hoc algorithms designed for the specific object and acquisition setup being monitored, with a strong focus on co-designing the acquisition and processing pipeline. Deep learning has overcome these limits providing greater flexibility and faster re-configuration. In this work, the process to be inspected consists in vials’ pack formation entering a freeze-dryer, which is a common scenario in pharmaceutical active ingredient packaging lines. To ensure that the machine produces proper packs, a vision system is installed at the entrance of the freeze-dryer to detect eventual anomalies with execution times compatible with the production specifications. Other constraints come from sterility and safety standards required in pharmaceutical manufacturing. This work presents an overview about the production line, with particular focus on the vision system designed, and about all trials conducted to obtain the final performance. Transfer learning, alleviating the requirement for a large number of training data, combined with data augmentation methods, consisting in the generation of synthetic images, were used to effectively increase the performances while reducing the cost of data acquisition and annotation. The proposed vision algorithm is composed by two main subtasks, designed respectively to vials counting and discrepancy detection. The first one was trained on more than 23k vials (about 300 images) and tested on 5k more (about 75 images), whereas 60 training images and 52 testing images were used for the second one.

Experimental characterization and modelling of a servo-pneumatic system for a knee loading apparatus

The new knee test rig developed in University of Bologna used pneumatic cylinder as actuator system. Specific characterization and modelling about the pneumatic cylinder and the related devices are needed in better controlling the test rig. In this thesis, an experimental environment for the related device is set up with data acquisition system using Real-time Windows Target, Simulink, MatLab. Based on the experimental data, a fitted model for the pneumatic cylinder friction is found.

Influence of adhesive thickness on adhesively bonded joints under fatigue loading

Research on adhesive joints is arousing increasing interest in aerospace industry. Incomplete knowledge of fatigue in adhesively bonded joints is a major obstacle to their application. The prediction of the disbonding growth is yet an open question. This thesis researches the influence of the adhesive thickness on fatigue disbond growth. Experimental testing on specimens with different thickness has been performed. Both a conventional approach based on the strain energy release rate and an approach based on cyclic strain energy are provided. The inadequacy of the former approach is discussed. Outcomes from tests support the idea of correlating the crack growth rate to the cyclic strain energy. In order to push further the study, a 2D finite element model for the prediction of disbond growth under quasi-static loading has been developed and implemented in Abaqus. Numerical simulations have been conducted with different values of the adhesive thickness. The results from tests and simulations are in accordance with each other. According to them, no dependence of disbonding on the adhesive thickness has been evidenced.